Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,8 @@ tags:
|
|
| 7 |
- midjourney
|
| 8 |
- text2image
|
| 9 |
- text to image
|
|
|
|
|
|
|
| 10 |
datasets:
|
| 11 |
- pszemraj/text2image-prompts-multi
|
| 12 |
widget:
|
|
@@ -34,9 +36,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 34 |
|
| 35 |
# OPT-350m-multiprompt-v1
|
| 36 |
|
|
|
|
|
|
|
| 37 |
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the pszemraj/text2image-prompts-multi dataset.
|
| 38 |
It achieves the following results on the evaluation set:
|
| 39 |
- Loss: 1.6669
|
|
|
|
|
|
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
|
|
|
| 7 |
- midjourney
|
| 8 |
- text2image
|
| 9 |
- text to image
|
| 10 |
+
- prompt augment
|
| 11 |
+
- prompt engineering
|
| 12 |
datasets:
|
| 13 |
- pszemraj/text2image-prompts-multi
|
| 14 |
widget:
|
|
|
|
| 36 |
|
| 37 |
# OPT-350m-multiprompt-v1
|
| 38 |
|
| 39 |
+
Generate/augment your prompt with a model trained on a large & diverse prompt dataset.
|
| 40 |
+
|
| 41 |
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the pszemraj/text2image-prompts-multi dataset.
|
| 42 |
It achieves the following results on the evaluation set:
|
| 43 |
- Loss: 1.6669
|
| 44 |
+
- eval steps per second: 16.21
|
| 45 |
+
- perplexity: 5.29
|
| 46 |
|
| 47 |
## Model description
|
| 48 |
|